matrx-batch

Cost-shield foundation for AI workloads in the Matrx ecosystem.

Three primitives:

OpenAI Batch API + Anthropic Message Batches — submit JSONL, poll status, fetch results. Async wrappers over the provider SDKs.
Urgency router — BatchRouter.submit(job) routes a job to live inference, to the provider's Batch API (50% discount, 24h SLA), or makes a cost-based decision automatically.
Embedding cache — content-addressable (SHA256 of model || text) reuse of embedding vectors across the org. Backed by rag.embedding_cache via a host-supplied asyncpg pool.

Dependency posture

matrx-batch sits one notch above matrx-utils in the dependency graph and is consumed by matrx-rag (embedding cache) and matrx-ai (urgency router, future). It MUST NOT import from aidream/ or from any other matrx-* sibling — every cross-boundary dependency comes in via matrx_batch.configure(...).

Usage (host-side wiring)

import matrx_batch
from openai import AsyncOpenAI
from anthropic import AsyncAnthropic

matrx_batch.configure(
    openai_client=AsyncOpenAI(api_key=settings.OPENAI_API_KEY),
    anthropic_client=AsyncAnthropic(api_key=settings.ANTHROPIC_API_KEY),
    pool_factory=lambda: get_async_pg_pool(),
    cost_check=_aidream_budget_precheck,
)

# Wire the cache into matrx-rag's embed() funnel
import matrx_rag
matrx_rag.configure(embedding_cache=matrx_batch.get_embedding_cache())

Usage (consumer)

from matrx_batch import BatchRouter, BatchableJob

router = BatchRouter()
receipt = await router.submit(
    BatchableJob(
        kind="chat",
        provider="anthropic",
        urgency="auto",
        payload={"model": "claude-haiku-4-5", "messages": [...]},
        estimated_tokens_in=8200,
    )
)

Release files for matrx-batch 0.2.108

For a detailed explanation of source distributions (sdists) and built distributions (wheels), please see the package formats documentation.

Source distribution (sdist)

Source distribution for matrx-batch 0.2.108
File	Size	Uploaded
matrx_batch-0.2.108.tar.gz	83.4 kB	Sep 25, 2026	Details

Built distribution (wheel)

Table of built distributions (wheels) for matrx-batch 0.2.108
File	Interpreter	ABI	Platform	Reset
matrx_batch-0.2.108-py3-none-any.whl 72.6 kB Sep 25, 2026	Python 3	none	any	Details

Total release size: 156.0 kB

Release files / matrx_batch-0.2.108.tar.gz

Download URL	matrx_batch-0.2.108.tar.gz
Size	83.4 kB
Tags	Source
SHA-256 checksum How to use checksums	`ffe28fe96245f50ea1c0bd216eedbb480db1d5f06271293748730eb768bcbdac`
BLAKE2b-256 checksum How to use checksums	`9a691af6e2a461cbde9c942046f98a0b8fffcdd99419a3699e6ee4f5480675d3`
Upload date	Sep 25, 2026
Uploaded using Trusted Publishing? What is trusted publishing?	Yes
Uploaded via	`twine/7.0.0 CPython/3.13.14`

Provenance

Provenance describes where a file came from. On PyPI, provenance is shared via attestations, which provide a verifiable record of the build or publishing details. View details, limitations and caveats.

Identity

Publishing platform: GitHub Actions
Publishing repository: github.com/AI-Matrix-Engine/aidream
Publishing commit: github.com/AI-Matrix-Engine/aidream/tree/bbad842b7e146bc60458111cf341153e2a8ce05f

Workflow

Publishing configuration: github.com/AI-Matrix-Engine/aidream/blob/bbad842b7e146bc60458111cf341153e2a8ce05f/.github/workflows/publish-package.yml
Publishing logs: github.com/AI-Matrix-Engine/aidream/actions/runs/36088866774/attempts/1

Artifact

Subject: matrx_batch-0.2.108.tar.gz
SHA-256 checksum: ffe28fe96245f50ea1c0bd216eedbb480db1d5f06271293748730eb768bcbdac Verifying attestations

Release files / matrx_batch-0.2.108-py3-none-any.whl

Download URL	matrx_batch-0.2.108-py3-none-any.whl
Size	72.6 kB
Tags	Python 3
SHA-256 checksum How to use checksums	`83ce5b59829e07ec7e54294dfd3abcd839c28ed6c843d07a87b29df91f7db8a4`
BLAKE2b-256 checksum How to use checksums	`2c09bd520e8d27bbce6e87d632c19888c3bfd72b22fba2bc009c599078a353ef`
Upload date	Sep 25, 2026
Uploaded using Trusted Publishing? What is trusted publishing?	Yes
Uploaded via	`twine/7.0.0 CPython/3.13.14`

Provenance

Identity

Publishing platform: GitHub Actions
Publishing repository: github.com/AI-Matrix-Engine/aidream
Publishing commit: github.com/AI-Matrix-Engine/aidream/tree/bbad842b7e146bc60458111cf341153e2a8ce05f

Workflow

Publishing configuration: github.com/AI-Matrix-Engine/aidream/blob/bbad842b7e146bc60458111cf341153e2a8ce05f/.github/workflows/publish-package.yml
Publishing logs: github.com/AI-Matrix-Engine/aidream/actions/runs/36088866774/attempts/1

Artifact

Subject: matrx_batch-0.2.108-py3-none-any.whl
SHA-256 checksum: 83ce5b59829e07ec7e54294dfd3abcd839c28ed6c843d07a87b29df91f7db8a4 Verifying attestations